復現視訊裡的程式碼，方便後續查閱。

import numpy as np
import torch
torch.cuda.current_device()
import torch.nn as nn

 
# 構造輸入資料x和其對應的標籤y
x_values=[i for i in range(11)]
x_train=np.array(x_values,dtype=np.float32)
x_train=x_train.reshape(-1,1)
y_values=[2*i+1 for i in x_values]
y_train=np.array(y_values,dtype=np.float32)
y_train=y_train.reshape(-1,1)
# 其實線性迴歸是不加啟用函式的全連線層
class LinearRegressionModel(nn.Module):
    def __init__(self,input_dim,output_dim):
        super(LinearRegressionModel,self).__init__()
        self.linear=nn.Linear(input_dim,output_dim)
    #     重寫前向傳播方法，繼承自module
    def forward(self,x):
        out=self.linear(x)
        return out
input_dim=1
output_dim=1
model=LinearRegressionModel(input_dim,output_dim)

device=torch.device("cuda:1" if torch.cuda.is_available() else "cpu" )
model.to(device)

criterion=nn.MSELoss()

#訓練次數
epochs=1000
#定義學習率
learning_rate=0.01
# 優化器選擇隨機梯度下降演算法
optimizer=torch.optim.SGD(model.parameters(),lr=learning_rate)
# 選擇損失函式MSE
criterion=nn.MSELoss()
 
for epoch in range(epochs):
    epoch+=1
    # 轉成tensor格式
    inputs=torch.from_numpy(x_train).to(device)
    labels=torch.from_numpy(y_train).to(device)
    # 每次迭代梯度清零，防止累加
    optimizer.zero_grad()
    # 前向傳播
    outputs=model(inputs)
    # 計算損失
    loss=criterion(outputs,labels)
    # 反向傳播
    loss.backward()
    # 更新權重引數
    optimizer.step()
    if epoch%50==0:
        print('epoch{},loss{}'.format(epoch,loss.item()))